INDEX

Explanations

references to changes and developments over time

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

asia

-0.15

iar

-0.15

iate

-0.14

bst

-0.14

Äı

-0.14

Pad

-0.14

uest

-0.14

bast

-0.14

egin

-0.13

iden

-0.13

POSITIVE LOGITS

/vnd

0.16

DidEnter

0.16

ANI

0.15

aterangepicker

0.15

 latter

0.15

Obr

0.15

 Phong

0.14

 Became

0.14

 became

0.14

Activations Density 0.136%

references to changes and developments over time

No Comments

No Known Activations